Method for identifying freshness of food materials in refrigerator and controlling odor removal system based on spectrum sensor

Through spectral sensors and intelligent decision-making algorithms, the gas concentration in the refrigerator is monitored in real time, which solves the problem that traditional refrigerators cannot monitor the freshness of food and air quality, and realizes the judgment of freshness of food and air quality control, extends the shelf life and improves the quality of life of users.

CN120292807APending Publication Date: 2025-07-11SHENZHEN VISPEK TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510344475.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-21
Publication Date
2025-07-11

AI Technical Summary

Technical Problem

Traditional refrigerators cannot monitor the freshness of ingredients in real time and cannot monitor and control the air quality in the refrigerator in real time, resulting in rotten ingredients and odors affecting health.

Method used

Spectral sensors are used to monitor the concentration of ammonia, hydrogen sulfide and alcohol gases in the refrigerator in real time, and combine intelligent decision-making algorithms to control the odor clean system to achieve accurate judgment of the freshness of food ingredients and control air quality.

Benefits of technology

It has achieved accurate judgment of the freshness of ingredients in the refrigerator and real-time improvement of air quality, extends the shelf life of ingredients, reduces waste, and improves users' quality of life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120292807A_ABST
    Figure CN120292807A_ABST
Patent Text Reader

Abstract

The invention discloses a method for identifying freshness of food materials in a refrigerator and controlling an odor removal system based on a spectrum sensor, which synchronously detects characteristic absorption spectrums of ammonia gas, hydrogen sulfide and alcohol gas through ultraviolet and infrared broadband scanning. The system constructs a multi-gas linear regression model, and three-level freshness early warning is realized in combination with a dynamic threshold value; if the concentration of the alcohol gas is less than 30 ppm, the fruits are first-grade fresh; when the concentration of ammonia gas is less than 10ppm, vegetables and meat are first-grade fresh; when the alcohol gas is greater than or equal to 30 ppm or the ammonia gas is greater than or equal to 10 ppm, the secondary freshness of the meat, the fruits or the vegetables is early warned; if hydrogen sulfide is detected, the third-level freshness is directly judged. Model training is based on a gas release rule in a refrigeration environment, false alarms are remarkably reduced, the food material safety window period is prolonged, and a low-cost and high-reliability freshness monitoring solution is provided for the intelligent refrigerator.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of smart home appliances, and particularly to a method for identifying the freshness of refrigerator ingredients based on a spectral sensor and controlling a deodorization system. Background Art

[0002] With the improvement of people's living standards, refrigerators have become indispensable appliances in households. However, most refrigerators on the market currently can only provide refrigeration and freezing functions and cannot accurately detect the freshness of ingredients. Ingredients will gradually deteriorate during storage, which not only affects the taste and nutritional value but may also pose a hazard to human health. In addition, most refrigerators on the market currently can only turn on and off the deodorization system at regular intervals and cannot identify odors and turn on the deodorization system in a timely manner. The odors and harmful gases in the refrigerator will also affect the storage quality of ingredients. Therefore, it is of great practical significance to develop a method that can detect the freshness of refrigerator ingredients in real time and effectively control the air quality in the refrigerator.

[0003] In view of the above problems, the present invention provides a method for detecting the freshness of refrigerator ingredients based on a spectral sensor and controlling a deodorization system. By detecting the concentration of specific gases in the refrigerator with a spectral sensor, the freshness of the ingredients is accurately judged, and the operation of the deodorization system is controlled according to the freshness situation to maintain the air quality in the refrigerator and the freshness of the ingredients. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for detecting the freshness of refrigerator ingredients based on a spectral sensor and controlling a deodorization system. The problems solved by the present invention are that traditional refrigerators cannot monitor the freshness of ingredients in the refrigerator in real time and cannot monitor the air in the refrigerator to turn on the deodorization system in real time. The freshness level of the current ingredients is divided by a spectral sensor that monitors the air (ammonia, hydrogen sulfide, alcohols) in the refrigerator in real time, and the operation of the deodorization system is controlled according to the freshness situation to achieve accurate analysis of the gas components inside the refrigerator, and combined with an intelligent decision-making algorithm to control the deodorization system to form a complete ingredient freshness preservation closed loop.

[0005] The present invention discloses a method for detecting the freshness of refrigerator ingredients based on a spectral sensor and controlling a deodorization system, including the following steps:

[0006] Step 1: Fix and install the sensor inside the refrigerator air duct.

[0007] The spectral sensor includes ultraviolet and infrared wavelengths. The acquisition frequency is 1 time / 5 min. After continuously acquiring three spectral data and filtering out abnormal data, the average value is input into the model.

[0008] Step 2: Collect the original spectral data of ammonia, hydrogen sulfide, and alcohol gases inside the closed refrigerator and train a linear regression model.

[0009] For the said collection, the sensor does not turn on when the refrigerator door is opened and starts after it is closed, avoiding the detection of abnormal data.

[0010] The ammonia collection concentration is 0 - 30 ppm, the alcohol gas collection concentration is 0 - 80 ppm, and the hydrogen sulfide gas collection concentration is 0 - 10 ppm;

[0011] The original spectral data collection environment is inside the refrigerator, and the collection temperature range is set at 0 - 10 °C to fit the actual scenario and reduce the influence of temperature and humidity on the sensor;

[0012] Step 3: Determine the freshness level according to the gas data collected in Step 2.

[0013] The said freshness levels include:

[0014] When the detected alcohol gas concentration is less than 30 ppm, remind the user that the fruit is in the first - level freshness, at this time the fruit is the freshest, with the best nutritional value and taste;

[0015] When the detected ammonia concentration is less than 10 ppm, remind the user that the vegetables and meats are in the first - level freshness, at this time the vegetables and meats are the freshest, with the best nutritional value and taste;

[0016] When the detected alcohol gas is greater than or equal to 30 ppm, remind the user that the fruit is in the second - level freshness, indicating that the fruit begins to show signs of spoilage and the taste and nutritional value begin to decline.

[0017] When the detected ammonia is greater than or equal to 10 ppm, remind the user that the meat products are in the second - level freshness, meaning that the vegetables and meats begin to deteriorate.

[0018] When hydrogen sulfide gas is detected, regardless of whether it is fruit or other food ingredients, it is determined that the food ingredients are in the third - level freshness, that is, the food ingredients have spoiled and are inedible.

[0019] Step 4: The odor - removal system turns on and off according to the freshness level.

[0020] The said odor - removal system is clicked to run through the APP or the refrigerator control panel before the customer's first use. After running for a period of time, three spectral data are collected, and after filtering out abnormal data, the average value is calculated and input into the model to update the 0 - point value of the model.

[0021] The said level switch includes:

[0022] When the prediction result is in the second - level freshness, the odor - removal system exhausts air at a rate of 20 m 3 / h and starts UV - C ultraviolet sterilization until the gas concentration returns within the spectral value of the first - level freshness;

[0023] When the prediction result is in the third - level freshness, the odor - removal system exhausts air at a rate of 40 m 3 / h, start UV-C ultraviolet sterilization until the gas concentration returns within the spectral value of primary freshness, and push a reminder to the user to discard the food ingredients.

[0024] The beneficial effects of the present invention are as follows:

[0025] 1. By using wide-band scanning of ultraviolet and infrared spectral sensors and combining with a linear regression model, it is possible to accurately detect the concentrations of gases such as ammonia, hydrogen sulfide, and alcohols in the refrigerator, thereby accurately judging the freshness of food ingredients and providing timely and accurate food ingredient freshness information to users.

[0026] 2. Automatically controlling the operation of the fresh air system according to the freshness of food ingredients can effectively improve the air quality in the refrigerator, extend the freshness preservation period of food ingredients, and reduce food ingredient waste.

[0027] 3. By setting different freshness reminders, users can timely understand the freshness of food ingredients in the refrigerator, reasonably arrange the use of food ingredients, avoid consuming spoiled food ingredients, and improve the quality of life of users. Description of the Drawings

[0028] The drawings here are incorporated into the specification and form a part of this specification, showing the embodiments in line with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.

[0029] Figure 1 : A method flow chart for identifying the freshness of refrigerator food ingredients and controlling the odor purification system based on spectral sensors;

[0030] Figure 2 : A fitting curve (R 2 = 0.97) diagram of the alcohol gas concentration and the spectral value; Detailed Embodiments

[0031] The following will clearly and completely describe and discuss the technical solutions in the embodiments of the present invention in conjunction with the drawings of the present invention. Obviously, what is described here is only a part of the examples of the present invention, not all examples. All other examples obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the protection scope of the present invention.

[0032] Embodiment 1:

[0033] The present invention discloses a method for detecting the freshness of refrigerator food ingredients and controlling the odor purification system based on spectral sensors, including the following steps:

[0034] Step 1. Fix the ultraviolet and infrared wavelength sensors in the refrigerator air duct, and control the data acquisition frequency to be 1 time / 5 min through an embedded program. Continuously collect three spectral data, remove abnormal data through filtering, and then calculate the average value and input it into the model.

[0035] Step 2: Inside the closed refrigerator, set the collection temperatures at 0°C and 10°C, collect the original spectral data of blank air, and release ammonia gas one by one with a concentration range of 0 - 30 ppm, hydrogen sulfide gas with a concentration range of 0 - 10 ppm, and alcohol gas with a concentration range of 0 - 80 ppm. Figure 2 After collecting each gas, ventilate and evacuate the air inside the refrigerator until the spectral data returns to that of blank air before proceeding with the collection of the next gas. After the collection is completed, train a linear regression model one by one. During the collection process, the sensor is not turned on when the refrigerator door is open and starts collecting after the refrigerator door is closed to avoid detecting abnormal data.

[0036] Step 3: Determine the freshness level based on the gas data collected in Step 2.

[0037] When the detected concentration of alcohol gas is less than 30 ppm, remind the user that the fruit is at the first - level freshness. At this time, the fruit is the freshest, with the best nutritional value and taste.

[0038] When the detected concentration of ammonia gas is less than 10 ppm, remind the user that the vegetables and meat are at the first - level freshness. At this time, the vegetables and meat are the freshest, with the best nutritional value and taste.

[0039] When the detected concentration of alcohol gas is greater than or equal to 30 ppm, remind the user that the fruit is at the second - level freshness, indicating that the fruit is starting to show signs of spoilage and the taste and nutritional value are starting to decline.

[0040] When the detected concentration of ammonia gas is greater than or equal to 10 ppm, remind the user that the meat products are at the second - level freshness, meaning that the vegetables and meat are starting to deteriorate.

[0041] When hydrogen sulfide gas is detected, regardless of whether it is fruit or other food ingredients, it is determined that the food ingredient is at the third - level freshness, that is, the food ingredient has spoiled and is inedible.

[0042] Starting from the first - level freshness, push the current freshness level to the user through the APP or the refrigerator control panel every 6 hours. If the freshness level is upgraded to the second - level freshness or the third - level freshness, it will be pushed immediately without being restricted by the 6 - hour limit.

[0043] Step 4: The odor - removal system is switched according to the freshness level. When the prediction result is at the second - level freshness, the odor - removal system exhausts air at a rate of 20 m 3 / h, starts UV - C ultraviolet sterilization until the gas concentration returns within the spectral value of the first - level freshness; when the prediction result is at the third - level freshness, the odor - removal system exhausts air at a rate of 40 m 3 / h, starts UV - C ultraviolet sterilization until the gas concentration returns within the spectral value of the first - level freshness, and pushes a reminder to discard the food ingredient to the user through the APP or the refrigerator control panel.

[0044] Click "Run" through the APP or the refrigerator control panel before the customer uses it for the first time. After running for a period of time, collect three spectral data, filter out abnormal data, calculate the average value, input it into the model, and update the zero-point value of the freshness model.

[0045] Step 5: Put the bananas picked in the same batch into the experimental refrigerator. The concentration of alcohol gas produced by the bananas is positively correlated with the apple maturity as shown in Table 1. When the freshness reaches the preset threshold level, the odor removal system is turned on. After it drops to the first-level threshold, the odor removal system is turned off, and the food ingredient status is pushed through the APP or the refrigerator control panel.

[0046] Time (h) Concentration (ppm) 0 0 6 2 12 6 18 9 24 13 30 15

[0047] After considering the specification and the practice disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

[0048] It should be understood that the present disclosure is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present disclosure should be limited by the appended claims.

Claims

1. A method for detecting the freshness of refrigerator ingredients and controlling the odor removal system based on a spectral sensor, characterized in that, It includes the following steps: Step 1: Fix and install the sensor inside the refrigerator air duct. Step 2: Collect the original spectral data of ammonia, hydrogen sulfide, and alcohol gases inside the closed refrigerator, and train a linear regression model. Step 3: Determine the freshness level based on the gas data collected in Step 2. Step 4: The odor removal system turns on and off according to the freshness level.

2. A method for detecting the freshness of refrigerator food materials and controlling the odor removal system based on a spectral sensor according to Step 1 of Claim 1, wherein: The spectral sensor includes ultraviolet and infrared wavelengths. The collection frequency is 1 time per 5 minutes. After collecting three spectral data and filtering out abnormal data, the average value is input into the model.

3. A method for detecting the freshness of refrigerator food materials and controlling the odor removal system based on a spectral sensor according to Step 2 of Claim 1, wherein: For the collection, the sensor does not turn on when the refrigerator door is open and starts after it is closed to avoid detecting abnormal data. The collection concentration of ammonia is 0 - 30 ppm, the collection concentration of alcohol gas is 0 - 80 ppm, and the collection concentration of hydrogen sulfide gas is 0 - 10 ppm; The original spectral data is collected inside the refrigerator, and the collection temperature range is set at 0 - 10 °C to fit the actual scenario and reduce the influence of temperature and humidity on the sensor.

4. A method for detecting the freshness of refrigerator ingredients and controlling the odor removal system based on a spectral sensor according to step 3 of claim 1, characterized in that, The freshness level includes: When the concentration of alcohol gas is detected to be less than 30 ppm, it reminds the user that the fruit is in the first - level freshness. At this time, the fruit is the freshest, with the best nutritional value and taste; When the concentration of ammonia is detected to be less than 10 ppm, it reminds the user that the vegetables and meat are in the first - level freshness. At this time, the vegetables and meat are the freshest, with the best nutritional value and taste; When the concentration of alcohol gas is detected to be greater than or equal to 30 ppm, it reminds the user that the fruit is in the second - level freshness, indicating that the fruit begins to show signs of spoilage, and the taste and nutritional value start to decline. When the concentration of ammonia is detected to be greater than or equal to 10 ppm, it reminds the user that the meat products are in the second - level freshness, meaning that the vegetables and meat begin to deteriorate. When hydrogen sulfide gas is detected, regardless of whether it is fruit or other food materials, it is determined that the food materials are in the third - level freshness, that is, the food materials have spoiled and are inedible.

5. A method for detecting the freshness of refrigerator food materials and controlling the odor removal system based on a spectral sensor according to Claim 1, wherein: The odor removal system is clicked to run through the APP or the refrigerator control panel before the customer's first use. After running for a period of time, three spectral data are collected, abnormal data is filtered out, and the average value is input into the model to update the 0 - point value of the model. The level switch includes: When the prediction result is at the secondary freshness level, the odor removal system exhausts air at a rate of 20 m 3 / h and starts UV-C ultraviolet sterilization until the gas concentration returns within the spectral value of the primary freshness level; When the prediction result is at the third-level freshness, the odor removal system operates at 40m 3 / h, starts UV-C ultraviolet sterilization until the gas concentration returns within the spectral value of the first-level freshness, and pushes a reminder to the user to discard the food ingredients.